AI Paper Atlas

Research map / Reinforcement learning / Policy gradient and actor-critic

Uncorrected Least-Squares Temporal Difference with Lambda-Return

Takayuki Osogami

AAAI 2020 · Reinforcement learning › Policy gradient and actor-critic · approach: Temporal-difference and discounting theory · 1 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
Use Boyan's LSTD(lambda) with optimal lambda and alpha instead of Uncorrected LSTD(lambda) with its optimal choicesLSTD(lambda) on random MRPs · small, large, deterministic MRPs with non-binary featuresMSE: up to 2 %Mixed
Use Uncorrected LSTD(lambda) rather than Boyan's across the range of lambda and alphaLSTD(lambda) · random MRPsMSE stability across hyperparametersImproved
Mix Uncorrected and Boyan's LSTD(lambda) with weight lambdaMixed LSTD(lambda) · random MRPsMSEMixed
Skip the bootstrap correction of Monte Carlo return (Uncorrected instead of Boyan's) in a stateless MRPLSTD(lambda) · stateless MRP, Proposition 1estimator varianceImproved
Skip the bootstrap correction of Monte Carlo return in a stateless MRPLSTD(lambda) · stateless MRP, Proposition 1estimator biasHurt

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy